From process signals to design decisions: towards a data-driven assistance system for hot bulk forging process design

The project DatProForge (Data-driven Process Modelling of Drop Forging Processes to Increase Productivity Using Adaptive Tool Design Methodology), conducted within the first funding period of SPP 2422 has established the foundations for an end-to-end digital process chain combining experimentally acquired process data, automated finite element (FE) simulations, radar-based condition monitoring, and data-driven and explainable artificial intelligence (XAI). The resulting methodology provides the basis for developing an intelligent assistant system for process design and optimisation. The intelligent assistant system employs machine learning (ML) and XAI methods to identify defect risks, determine their key influencing factors in a transparent manner, and generate recommendations for process optimisation and adaptive tool design. Using a hot bulk forging process on a servo screw forging press as a representative use case, the paper demonstrates how research results on sensor systems, radar signal processing, stochastic simulation, underfill prediction, vent-channel optimisation, and data-pipeline modelling can be integrated into a unified assistance system. Particular attention is given to the joint analysis of simulation results and experimentally acquired process data to identify relevant process and machine-related effects and to account for associated uncertainties. The resulting simulation-to-reality transfer approach enables the FE models to be successively refined by incorporating these effects, thereby progressively improving their agreement with the real forging process. Combined with interpretable data-driven models, this approach provides a foundation for robust, data-driven decision-making in process optimisation and adaptive tool design.

Authors

Institutions

Publication Details

Journal
Production Engineering
Published
2026-11-18
DOI
https://doi.org/10.1007/s11740-026-01483-x
Primary Topic
Metal Forming Simulation Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

From process signals to design decisions: towards a data-driven assistance system for hot bulk forging process design

Sebastian Härtel, Artem� Alimov, Markus Gardill, Yuyao Jiang
3 links
Production Engineering
Metal Forming Simulation Techniques
article

From process signals to design decisions: towards a data-driven assistance system for hot bulk forging process design

Sebastian Härtel, Artem� Alimov, Markus Gardill, Yuyao Jiang
article en

Abstract

The project DatProForge (Data-driven Process Modelling of Drop Forging Processes to Increase Productivity Using Adaptive Tool Design Methodology), conducted within the first funding period of SPP 2422 has established the foundations for an end-to-end digital process chain combining experimentally acquired process data, automated finite element (FE) simulations, radar-based condition monitoring, and data-driven and explainable artificial intelligence (XAI). The resulting methodology provides the basis for developing an intelligent assistant system for process design and optimisation. The intelligent assistant system employs machine learning (ML) and XAI methods to identify defect risks, determine their key influencing factors in a transparent manner, and generate recommendations for process optimisation and adaptive tool design. Using a hot bulk forging process on a servo screw forging press as a representative use case, the paper demonstrates how research results on sensor systems, radar signal processing, stochastic simulation, underfill prediction, vent-channel optimisation, and data-pipeline modelling can be integrated into a unified assistance system. Particular attention is given to the joint analysis of simulation results and experimentally acquired process data to identify relevant process and machine-related effects and to account for associated uncertainties. The resulting simulation-to-reality transfer approach enables the FE models to be successively refined by incorporating these effects, thereby progressively improving their agreement with the real forging process. Combined with interpretable data-driven models, this approach provides a foundation for robust, data-driven decision-making in process optimisation and adaptive tool design.

Production EngineeringVol. 21(1)
Brandenburg University of Technology Cottbus-Senftenberg (DE)
Industry, innovation and infrastructure
Metal Forming Simulation Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon